AWS c6id Benchmark Charts (2026071322)
AWS 32コア物理環境における VMemKV と RocksDB の包括的な性能ベンチマーク結果。各グラフの下部アコーディオンから、個別ディスカッション（Giscus）が行えます。
Stacking Variants
- RocksDB: 競合比較対象の LSM-Tree
- Baseline: 最適化なし状態の VMemKV
- +BF: Baseline + T1 Bloom Filter (空振りGet高速化)
- +Simd: + Bloom Filter + SIMD Scan (レンジスキャン線形走査高速化)
- +Hint: + SIMD + T2 Memory Hints (Compaction/Reorg時のI/Oストール緩和)
- +Inline: + Hints + T1 Inline Value (8B以下インメモリ値をT1スロットへ直接保存)
- +Prefault: + Inline + T2 Async Prefaulting (全部盛り / 最適化オールオン)
Environment
- CPU: Intel(R) Xeon(R) Platinum 8375C CPU @ 2.90GHz (32 Cores / 64 Threads)
- Cache: L1D 48KB, L1I 32KB, L2 1.25MB (per 2 cpus) | L3 54MB (per 32 cpus)
- RAM: Total 66.3 GB (In LTM runs, RAM is constrained to 1GiB cgroup)
- OS / Kernel: Ubuntu 22.04 LTS (Linux 6.17.0-1019-aws)
- Compiler: GCC / CMake Release Build
- Disk: Local NVMe SSD (AWS Instance Store, Swap Media)
Overall Notes & Annotations
このベンチマーク実験全体に対する考察やアノテーションメモをローカルに保存できます（ブラウザの localStorage に自動保存されます）。
Insert Workload
実験概要: Measures write throughput when inserting unique keys sequentially into empty/pre-populated store.
Update (Zipf) Workload
実験概要: Measures update throughput under Zipf access distribution (stateful updates).
Delete (Zipf) Workload
実験概要: Measures concurrent delete throughput (T1 index removals).
Get Miss (Zipf) Workload
実験概要: Evaluates read throughput for non-existent keys (tests Bloom Filter efficiency).
Get Hit (Zipf) Workload
実験概要: Measures point lookups for existing keys under Zipf distribution (cache-friendly).
Get Hit (Uniform) Workload
実験概要: Measures point lookups for existing keys under Uniform distribution (extreme cache misses).
Scan (No Reorg - Zipf) Workload
実験概要: Executes 100-key range queries under Zipf distribution with active append region.
Scan (No Reorg - Uniform) Workload
実験概要: Executes 100-key range queries under Uniform distribution (strict sequential prefetching).
Scan (With Reorg - Zipf) Workload
実験概要: Executes range queries after reorganize, pointing to a fully sorted in-memory region (Zipf).
Scan (With Reorg - Uniform) Workload
実験概要: Executes range queries after reorganize, pointing to a fully sorted in-memory region (Uniform).
Insert Workload
実験概要: Measures write throughput when inserting unique keys sequentially into empty/pre-populated store.
Update (Zipf) Workload
実験概要: Measures update throughput under Zipf access distribution (stateful updates).
Delete (Zipf) Workload
実験概要: Measures concurrent delete throughput (T1 index removals).
Get Miss (Zipf) Workload
実験概要: Evaluates read throughput for non-existent keys (tests Bloom Filter efficiency).
Get Hit (Zipf) Workload
実験概要: Measures point lookups for existing keys under Zipf distribution (cache-friendly).
Get Hit (Uniform) Workload
実験概要: Measures point lookups for existing keys under Uniform distribution (extreme cache misses).
Scan (No Reorg - Zipf) Workload
実験概要: Executes 100-key range queries under Zipf distribution with active append region.
Scan (No Reorg - Uniform) Workload
実験概要: Executes 100-key range queries under Uniform distribution (strict sequential prefetching).
Scan (With Reorg - Zipf) Workload
実験概要: Executes range queries after reorganize, pointing to a fully sorted in-memory region (Zipf).
Scan (With Reorg - Uniform) Workload
実験概要: Executes range queries after reorganize, pointing to a fully sorted in-memory region (Uniform).
Insert Workload
実験概要: Measures write throughput when inserting unique keys sequentially into empty/pre-populated store.
Update (Zipf) Workload
実験概要: Measures update throughput under Zipf access distribution (stateful updates).
Delete (Zipf) Workload
実験概要: Measures concurrent delete throughput (T1 index removals).
Get Miss (Zipf) Workload
実験概要: Evaluates read throughput for non-existent keys (tests Bloom Filter efficiency).
Get Hit (Zipf) Workload
実験概要: Measures point lookups for existing keys under Zipf distribution (cache-friendly).
Get Hit (Uniform) Workload
実験概要: Measures point lookups for existing keys under Uniform distribution (extreme cache misses).
Scan (No Reorg - Zipf) Workload
実験概要: Executes 100-key range queries under Zipf distribution with active append region.
Scan (No Reorg - Uniform) Workload
実験概要: Executes 100-key range queries under Uniform distribution (strict sequential prefetching).
Scan (With Reorg - Zipf) Workload
実験概要: Executes range queries after reorganize, pointing to a fully sorted in-memory region (Zipf).
Scan (With Reorg - Uniform) Workload
実験概要: Executes range queries after reorganize, pointing to a fully sorted in-memory region (Uniform).